基于深度卷积神经网络的供电系统通信电源逆变器故障诊断  

Fault Diagnosis of Communication Power Supply Inverter of Power Supply System Based on Deep Convolutional Neural Network

作　　者：李跃 LI Yue(State Grid Hebei Baoding Mancheng District Power Supply Company,Baoding 072150,China)

机构地区：[1]国网河北省保定市满城区供电公司,河北保定072150

出　　处：《通信电源技术》2024年第24期132-134,共3页Telecom Power Technology

摘　　要：针对10kV供电系统三电平通信电源逆变器易受噪声干扰、故障诊断较为困难的问题,提出一种基于深度卷积神经网络的供电系统通信电源逆变器故障诊断方法。通过采集并转换逆变器的输出电流信号,得到电流信号的时域形式,完成故障信号特征的提取。基于深度卷积神经网络理论,构建供电系统通信电源逆变器故障诊断模型,实现供电系统通信电源逆变器故障诊断。测试表明,该方法故障诊断时间较短,且故障诊断结果较为精准,在第66次迭代时可实现零误差故障定位,应用效果较好。Aiming at the problem that the inverter of three-level communication power supply in 10 kV power supply system is easily disturbed by noise and the fault diagnosis is difficult,this paper proposes a fault diagnosis method of communication power supply inverter in power supply system based on deep convolution neural network.By collecting and converting the output current signal of the inverter,the time domain form of the current signal is obtained,and the characteristics of the fault signal are extracted.On this basis,based on the theory of deep convolution neural network,the fault diagnosis model of communication power inverter in power supply system is constructed to realize the fault diagnosis of communication power inverter in power supply system.The test shows that the fault diagnosis time of this method is short,and the fault diagnosis result is more accurate.The fault location with zero error can be realized in the 66th iteration,and the application effect is good.

关 键 词：10KV供电系统 三电平逆变器 通信电源 故障诊断 时域转换 

分 类 号：TN929.5[电子电信—通信与信息系统] TN86[电子电信—信息与通信工程]